Many of the ML/AI tasks typically deal with data represented in the Euclidean space, e.g., image classification, speech recognition. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects.
Graph data contains rich relation information among its elements, however, the complexity of graph data has imposed significant challenges on existing AI systems. In this field, I focused on extracting information from Knowledge Graphs (KG), which lead to several scientific contributions.
Google Scholar: